ext3: allow specifying external journal by pathname mount option

It's always been a hassle that if an external journal's
device number changes, the filesystem won't mount.
And since boot-time enumeration can change, device number
changes aren't unusual.

The current mechanism to update the journal location is by
passing in a mount option w/ a new devnum, but that's a hassle;
it's a manual approach, fixing things after the fact.

Adding a mount option, "-o journal_path=/dev/$DEVICE" would
help, since then we can do i.e.

# mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ...

and it'll mount even if the devnum has changed, as shown here:

# losetup /dev/loop0 journalfile
# mke2fs -L mylabel-journal -O journal_dev /dev/loop0
# mkfs.ext3 -L mylabel -J device=/dev/loop0 /dev/sdb1

Change the journal device number:

# losetup -d /dev/loop0
# losetup /dev/loop1 journalfile

And today it will fail:

# mount /dev/sdb1 /mnt/test
mount: wrong fs type, bad option, bad superblock on /dev/sdb1,
       missing codepage or helper program, or other error
       In some cases useful info is found in syslog - try
       dmesg | tail  or so

# dmesg | tail -n 1
[17343.240702] EXT3-fs (sdb1): error: couldn't read superblock of external journal

But with this new mount option, we can specify the new path:

# mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test
#

(which does update the encoded device number, incidentally):

# umount /dev/sdb1
# dumpe2fs -h /dev/sdb1 | grep "Journal device"
dumpe2fs 1.41.12 (17-May-2010)
Journal device:	          0x0701

But best of all we can just always mount by journal-path, and
it'll always work:

# mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test
#

So the journal_path option can be specified in fstab, and as long as
the disk is available somewhere, and findable by label (or by UUID),
we can mount.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>

diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 293855e950000ce53223d137b094d266d7911ad3..7ed0d17d67218597c33b46e391a095ca0e3e5aa2 100644 (file)
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -26,11 +26,12 @@ journal=inum                When a journal already exists, this option is ignored.
                        Otherwise, it specifies the number of the inode which
                        will represent the ext3 file system's journal file.
 
                        Otherwise, it specifies the number of the inode which
                        will represent the ext3 file system's journal file.
 

+journal_path=path

 journal_dev=devnum     When the external journal device's major/minor numbers
 journal_dev=devnum     When the external journal device's major/minor numbers

-                       have changed, this option allows the user to specify
+                       have changed, these options allow the user to specify

                        the new journal location.  The journal device is
                        the new journal location.  The journal device is

-                       identified through its new major/minor numbers encoded
-                       in devnum.
+                       identified through either its new major/minor numbers
+                       encoded in devnum, or via a path to the device.

 
 norecovery             Don't load the journal on mounting. Note that this forces
 noload                 mount of inconsistent filesystem, which can lead to
 
 norecovery             Don't load the journal on mounting. Note that this forces
 noload                 mount of inconsistent filesystem, which can lead to

diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index c47f147507227fda66d6b1a59e6922ab60e36ff9..c50c76190373a06bdb1a7971a935e7a5d00d9888 100644 (file)
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -27,6 +27,7 @@
 #include <linux/seq_file.h>
 #include <linux/log2.h>
 #include <linux/cleancache.h>
 #include <linux/seq_file.h>
 #include <linux/log2.h>
 #include <linux/cleancache.h>

+#include <linux/namei.h>

 
 #include <asm/uaccess.h>
 
 
 #include <asm/uaccess.h>
 


@@ -819,6 +820,7 @@ enum {
        Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
        Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
        Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
        Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
        Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
        Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,

+       Opt_journal_path,

        Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
        Opt_data_err_abort, Opt_data_err_ignore,
        Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
        Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
        Opt_data_err_abort, Opt_data_err_ignore,
        Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,


@@ -860,6 +862,7 @@ static const match_table_t tokens = {
        {Opt_journal_update, "journal=update"},
        {Opt_journal_inum, "journal=%u"},
        {Opt_journal_dev, "journal_dev=%u"},
        {Opt_journal_update, "journal=update"},
        {Opt_journal_inum, "journal=%u"},
        {Opt_journal_dev, "journal_dev=%u"},

+       {Opt_journal_path, "journal_path=%s"},

        {Opt_abort, "abort"},
        {Opt_data_journal, "data=journal"},
        {Opt_data_ordered, "data=ordered"},
        {Opt_abort, "abort"},
        {Opt_data_journal, "data=journal"},
        {Opt_data_ordered, "data=ordered"},


@@ -975,6 +978,11 @@ static int parse_options (char *options, struct super_block *sb,
        int option;
        kuid_t uid;
        kgid_t gid;
        int option;
        kuid_t uid;
        kgid_t gid;

+       char *journal_path;
+       struct inode *journal_inode;
+       struct path path;
+       int error;
+

 #ifdef CONFIG_QUOTA
        int qfmt;
 #endif
 #ifdef CONFIG_QUOTA
        int qfmt;
 #endif


@@ -1129,6 +1137,41 @@ static int parse_options (char *options, struct super_block *sb,
                                return 0;
                        *journal_devnum = option;
                        break;
                                return 0;
                        *journal_devnum = option;
                        break;

+               case Opt_journal_path:
+                       if (is_remount) {
+                               ext3_msg(sb, KERN_ERR, "error: cannot specify "
+                                      "journal on remount");
+                               return 0;
+                       }
+
+                       journal_path = match_strdup(&args[0]);
+                       if (!journal_path) {
+                               ext3_msg(sb, KERN_ERR, "error: could not dup "
+                                       "journal device string");
+                               return 0;
+                       }
+
+                       error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
+                       if (error) {
+                               ext3_msg(sb, KERN_ERR, "error: could not find "
+                                       "journal device path: error %d", error);
+                               kfree(journal_path);
+                               return 0;
+                       }
+
+                       journal_inode = path.dentry->d_inode;
+                       if (!S_ISBLK(journal_inode->i_mode)) {
+                               ext3_msg(sb, KERN_ERR, "error: journal path %s "
+                                       "is not a block device", journal_path);
+                               path_put(&path);
+                               kfree(journal_path);
+                               return 0;
+                       }
+
+                       *journal_devnum = new_encode_dev(journal_inode->i_rdev);
+                       path_put(&path);
+                       kfree(journal_path);
+                       break;

                case Opt_noload:
                        set_opt (sbi->s_mount_opt, NOLOAD);
                        break;
                case Opt_noload:
                        set_opt (sbi->s_mount_opt, NOLOAD);
                        break;